GSBF-YOLO: A steel strip surface defect detection technique based on improved YOLOv8
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The application of deep learning algorithms in defect detection systems has become widespread. However, due to the low contrast of strip surface defects and the surrounding interference information. As a result, the false detection rate and missing rate of strip surface defect detection are high. The existing methods can not meet the large-scale application in strip surface defect detection. In this paper, we propose a precise and efficient detection model, GSBF-YOLO, which is based on YOLOv8 for detecting surface defects in strip steel. The Bidirectional Feature Pyramid Network module was added to the algorithm. More efficient feature fusion is achieved through bidirectional feature flow and weighted feature fusion. In addition, we designed an improved Grouped Spatial CConvolution module in Neck. The GSCConv enhances parameter utilization efficiency through packet convolution and integration of additional feature fusion layers. In order to verify the effectiveness of GSBF-YOLO algorithm. We perform experiments on the NEU-DET dataset. The results demonstrate that, with regards to the NEU-DET data set, the indices of mAP@0.5 and mAP@0.5:0.95 for the GSBF-YOLO model have undergone an increase of 3% and 0.4% respectively. Further, experimental results demonstrate that the GSBF-YOLO algorithm exhibits outstanding performance in the domain of strip surface defect detection.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it